Introduction
A LoRA model trained with ~290 images by RyanReos. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.5 version YesMix (because 1.6 version consists of some LoRAs that may affect the results).
Cautions (Must Read)
Some preview images are generated using hires fix. Thus, if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.
The maximum of generating resolution should not exceed 1024 theoretically, otherwise extra/deformed head/limbs will be waiting for you :). Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.
For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, make sure add '--no-half-vae' in command line of webui to prevent generating black images. See voldy's log for the details of edit method. For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.
Description
FAQ
Comments (9)
Did you train on any of the irelia pictures? Can't really get her. Else seems quite nice.
Maybe no pictures because i don't know who is irelia
@zakp she's another character of Ryanrose I'll send some pic on other comment
@zakp If you have plans for v2.0. Give me a contact information. I will package the pictures of ryanreos in my collection and send them to you. civitai cannot send private letters. But it will take some time to find
how many roles of RyanReos?succubus,primrose and ? what's their trigger words? Any way thanks:)
theoretically there is no need to create trigger tags for stylized lora, but i add 'ryanreos' in description of dataset and you can try it.
Wow, thanks for sharing, i loved this model from Ryan!
Nice , but can you make a Daraz18aka lora?please
Could you make a artstyle LoRa for ttrop (Artist)
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.